Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    topics related to refugee issues and social inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atak
    -0.17
     Aydın
    -0.15
    iani
    -0.15
    ãĤ¤ãĤº
    -0.14
    atched
    -0.14
    éĿ©åij½
    -0.14
    orest
    -0.14
     femin
    -0.14
    tvrt
    -0.14
    roid
    -0.13
    POSITIVE LOGITS
     tolerance
    0.40
    tol
    0.30
     tolerant
    0.28
     dialogue
    0.27
     peace
    0.25
     unity
    0.25
     diversity
    0.24
     toler
    0.24
    olerance
    0.24
     bridge
    0.23
    Act Density 0.262%

    No Known Activations